EP2411831B1 - Standorterkennungssystem und -verfahren mit fingerabdrücken - Google Patents

Standorterkennungssystem und -verfahren mit fingerabdrücken Download PDF

Info

Publication number
EP2411831B1
EP2411831B1 EP10715356.1A EP10715356A EP2411831B1 EP 2411831 B1 EP2411831 B1 EP 2411831B1 EP 10715356 A EP10715356 A EP 10715356A EP 2411831 B1 EP2411831 B1 EP 2411831B1
Authority
EP
European Patent Office
Prior art keywords
nodes
field devices
signal strengths
target device
signal strength
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Not-in-force
Application number
EP10715356.1A
Other languages
English (en)
French (fr)
Other versions
EP2411831A1 (de
Inventor
Philip Andrew Rudland
Peter Stephen May
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Koninklijke Philips NV
Original Assignee
Koninklijke Philips NV
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Koninklijke Philips NV filed Critical Koninklijke Philips NV
Publication of EP2411831A1 publication Critical patent/EP2411831A1/de
Application granted granted Critical
Publication of EP2411831B1 publication Critical patent/EP2411831B1/de
Not-in-force legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/12—Computing arrangements based on biological models using genetic models
    • G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S11/00—Systems for determining distance or velocity not using reflection or reradiation
    • G01S11/02—Systems for determining distance or velocity not using reflection or reradiation using radio waves
    • G01S11/06—Systems for determining distance or velocity not using reflection or reradiation using radio waves using intensity measurements
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
    • G01S5/0252—Radio frequency fingerprinting
    • G01S5/02521—Radio frequency fingerprinting using a radio-map

Definitions

  • the technical field of this disclosure is location detection systems and methods, particularly, location detection systems and methods with fingerprinting.
  • Wireless communication and control networks are becoming increasingly popular for home automation, building automation, healthcare infrastructure, low power cable-less links, asset control, and other applications.
  • One benefit of such networks is the ability to locate a network device or tag. For example, lighting commissioning personnel can quickly identify a specific wireless device, so installation costs can be reduced.
  • Expensive equipment may be tagged, and tracked in and around a building, allowing staff to easily locate the tagged equipment when needed for use, in an emergency, or for calibration. Tagged equipment can also generate an alarm when moved beyond specified boundaries.
  • a wireless communication and control network is a ZigBee network, which is a low cost, low power, wireless standard using the ZigBee protocol operating on top of the IEEE 802.15.4 wireless standard.
  • wireless devices can be located by estimating the distance from a number of fixed points and triangulating the location from the distance estimates, the accuracy of the location depends on the accuracy of the distance estimates.
  • Two methods of estimating distance are time of flight and signal strength.
  • the distance for a time of flight distance estimate is computed from the time for a signal to pass from one point to another and the expected signal velocity.
  • the distance for a signal strength distance estimate is computed from the decrease in signal strength and the expected signal strength decay.
  • the bandwidth of some wireless communication and control networks is too narrow to make a time of flight distance estimate.
  • the signal strength of some wireless communication and control networks varies widely with position due to attenuation and reflection from objects such as walls and people, typically preventing either a time of flight distance estimate or a signal strength distance estimate.
  • Another approach to location detection has been fingerprinting.
  • Signal strengths are measured over the area of the wireless communication and control network to determine a set of fingerprints for the area, i.e., a map of signal strengths from nearby devices for any location within the area.
  • a device to be located measures the signal strength from the devices at known locations around it.
  • the measured signal strengths are compared to the set of fingerprints to determine the location of the device.
  • determining the set of fingerprints of the area is time and labor intensive, making the process expensive.
  • the comparison between the measured signal strengths and the set of fingerprints requires comparison over the whole set of fingerprints, requiring a great deal of computational effort and time.
  • US Patent Application No. 2005/0014518 discloses a method of estimating the location of a wireless terminal wherein the location of a wireless terminal can be estimated by comparing the signal strength it currently observes against a map or database that correlates locations to signal strengths.
  • US Patent Application No. 2001/0022558 discloses a location system for wireless telecommunication infrastructures. This system uses a plurality of MS locating technologies including those based on: (1) two-way TOA and TDOA; (2) pattern recognition; (3) distributed antenna provisioning; and (4) supplemental information from various types of very low cost noninfrastructure base stations for communicating via a typical commercial wireless base station infrastructure or a public telephone switching network.
  • One aspect of the present invention focuses on a location detection method including defining nodes in an area, the area being associated with field devices and a target device; determining expected signal strengths from the field devices at the nodes, each expected signal strength at a particular node being associated with one of the field devices ; measuring actual signal strengths from the field devices at the target device for each of the field devices in communication with the target device, each actual signal strength being associated with one of the field devices; designating as valid nodes only the nodes having the expected signal strength for each field device in communication with the target device being greater than or equal to the actual signal strength for the respective field device; and determining, as the location of the target device, one of the valid nodes for which the actual signal strengths for the field devices agree with the expected signal strengths for the field devices at said one of the valid nodes
  • a location detection system including a target device; field devices; and a processor.
  • the processor is operable to determine expected signal strengths from the field devices at nodes in an area, each expected signal strength at a particular node being associated with one of the field devices; measure actual signal strengths from the field devices at the target device for each of the field devices in communication with the target device, each actual signal strength being associated with one of the field devices; designate as valid nodes only the nodes having the expected signal strength for a each field device in communication with the target device being is greater than or equal to the actual signal strength for the respective field device; and determine, as the location of the target device, one of the valid nodes for which the actual signal strengths for the field devices agree with the expected signal strengths for the field devices at said one of the valid nodes.
  • FIG. 1 is a schematic diagram of a location detection system in accordance with various embodiments of the present invention. A number of field devices associated with an area are used to locate a target device in the area.
  • the location detection system 20 includes a number of field devices 30 and at least one target device 40 .
  • the field devices 30 are associated with an area 50 that includes a number of nodes 52.
  • the field devices 30 are at known positions relative to the area 50 .
  • the target device 40 is at an unknown position relative to the area 50 and is the device for which location is to be determined.
  • the field devices 30 can be in communication with each other and with the target device 40.
  • the field devices 30 and/or the target device 40 can also be in communication with an optional control unit 60, which is in or out of the area 50. In another embodiment, the optional control unit 60 can be included in one of the field devices 30 or the target device 40.
  • Obstructions 62 in or out of the area 50 can attenuate and/or reflect signals between the target device 40 and the field devices 30, changing the signal strength at the nodes 52 from the signal strength that would occur were the obstructions 62 not present.
  • Exemplary obstructions include walls, people, furniture, and the like.
  • the location detection system 20 can also include an optional sensing device 64, such as a mobile location sensor for measuring an actual node location or a device for measuring an actual secondary location parameter, such as WiFi signal strength, temperature, electrical noise, light level, sound level, and the like.
  • the optional sensing device 64 can be used to provide feedback as to the accuracy of the location detection or can be used to provide additional input to the modeling of the field devices and their surroundings in the area.
  • the area 50 can be any area associated with a number of field devices 30, which can be in or out of the area 50 and on or off the nodes 52.
  • the nodes 52 in the area 50 can be defined in any pattern desired for a particular application. In this example, the nodes 52 are arranged in a Cartesian grid.
  • the nodes 52 can be defined in two or three dimensions with spacing as required by the desired accuracy in locating the target device 40 and as allowed by the computational resources available.
  • the field devices 30 communicate wirelessly with the target device 40.
  • the field devices 30 and the target device 40 can communicate using any desired protocol, such as a ZigBee protocol operating on top of the IEEE 802.15.4 wireless standard, WiFi protocol under IEEE standard 802.11 (such as 802.11b/g/n), Bluetooth protocol, Bluetooth Low Energy protocol, or the like.
  • ZigBee protocol systems typically have a large number of field devices at fixed reference points, especially if the lighting infrastructure uses ZigBee protocol for wireless control.
  • the field devices 30 can be fixed or moveable, as long as the position of the field devices 30 is known when locating the target device 40.
  • the location of at least on field device can be estimated from a known position of a fixed field device. Thus, the location of all the field devices is not required when beginning the location detection.
  • FIG. 2 is a block diagram of a wireless device for use with a location detection system and method in accordance with various embodiments of the present invention.
  • the wireless device can be a field device or a target device.
  • the wireless device can be a transmitter, a receiver, or a transmitter and receiver, and can be moveable or fixed.
  • the wireless device 70 includes memory storage 72, a processor 74, a transmitter portion 76, and a receiver portion 78.
  • the memory storage 72 can be any memory storage suitable for storing data and/or instructions.
  • the memory storage 72 exchanges information with the processor 74, which controls operation of the wireless device 70.
  • the transmitter portion 76 and receiver portion 78 communicate wirelessly with other wireless devices and/or central control centers, and can include antennas.
  • the transmitter portion 76 can receive data and instructions from the processor 74, and transmit a signal from the wireless device 70.
  • the receiver portion 78 can receive a signal from outside the wireless device 70, and provide data and instructions to the processor 74.
  • the wireless device 70 can operate as a transmitter, a receiver, or a transmitter and receiver.
  • the transmitter portion 76 can be omitted and the wireless device 70 operated as a receiver.
  • the receiver portion 78 can be omitted and the wireless device 70 operated as a transmitter.
  • the wireless device 70 operates under the ZigBee communications protocol operating on top of the IEEE 802.15.4 wireless standard.
  • the wireless device 70 operates under the WiFi protocol under IEEE standard 802.11 (such as 802.11b/g/n), Bluetooth protocol, Bluetooth Low Energy protocol, or the like.
  • the wireless device 70 can operate under any wireless protocol desired for a particular application.
  • the wireless device can be associated with another object, such as a lighting fixture, lighting control unit, asset to be tracked, a medical patient, or any other object.
  • the wireless device can also control and/or monitor the associated object.
  • the wireless device 70 can send and receive signals at a single carrier frequency or at a number of carrier frequencies. Wave length changes with carrier frequency, so the sensitivity to obstructions and interaction between signals from different field devices, such as null points, change with different carrier frequencies.
  • the processor 74 can switch operation of the wireless device 70 between different carrier frequencies.
  • the processor 74 can be a number of processors located with the wireless device 70 or at another location as required for computing power and ease of data communication.
  • the processor includes processors at each wireless device and a central processor at the optional control unit in communication with the wireless devices.
  • FIG. 3 is a flowchart of a location detection method in accordance with some embodiments of the present invention.
  • the method 100 includes defining nodes in an area 102, the area being associated with field devices and a target device; determining expected signal strengths from the field devices at the nodes 104, each expected signal strength at a particular node being associated with one of the field devices; measuring actual signal strengths from the field devices at the target device 106 for each of the field devices in communication with the target device, each actual signal strength being associated with one of the field devices; designating as valid nodes the nodes having the expected signal strength for a particular field device that is greater than or equal to the actual signal strength for a particular field device 108; and determining at least one of the valid nodes for which the actual signal strengths for the field devices agree with the expected signal strengths for the field devices at the at least one of the valid nodes 110.
  • the method 100 can be carried out with a location detection system as described in FIGS. 1 &2 above. Computational operations can be carried out at the processor in the
  • the defining nodes in an area 102 establishes the area in which the target device can be located.
  • the field devices can be outside the area as long as the radio frequency signals which they generate are in the area or radio frequency signals which they receive originate from the area.
  • the field devices can be fixed or moveable, but are at known positions relative to the area.
  • the field devices generate radio frequency signals, some or all of which are received by the target device.
  • the target device generates radio frequency signals, which are received by some or all of the field devices.
  • the expected signal strengths can be determined by various methods of modeling the field devices and their surroundings in the area.
  • Each record for a field device node which corresponds to a field device originating a signal, can include data such as: the identity of the field-device node (Node A; Node B; ...; Node X), the coordinates for the field device node (Ax, Ay; Bx, By; ...; Xx, Xy), the signal level for the field device node (SignalLevelAtA; SignalLevelAtB;...; SignalLevelAtX), and any other data for the field device node as desired for a particular application.
  • the data can be entered through a hard-coded program by automatic deduction or manually through some other user interface.
  • An expected signal strength for each node in the area from each field device can be calculated from the records for the field device nodes.
  • An expected signal record can be constructed for each node x,y in the grid (at coordinates x,y) with record RecordContents (x,y) equal to signalLevelFromNodeA ; signalLevelFromNodeB ; ... ; signalLevelFromNodeX , including signal levels at the node from each of the field device nodes.
  • the signal levels values can be determined by calculating the distance from the field device node to the node and estimating the decrease in signal strength at that distance.
  • the distance from the field device node A (Ax, Ay) to the node (x,y) equals the square root of [(Ax - x) ⁇ 2 + (Ay-y) ⁇ 2].
  • the signal levels value SignalLevelFromNodeA at the node x,y equals the SignalLevelAtA * fn(distance of node x,y from field device node A), where the function fn(x) returns an estimate of the remaining signal strength at distance x from the source.
  • the function fn(x) equals (x ⁇ -3.5). The calculation is performed for each node in the area for each field device node, populating the records RecordContents (x,y) for all nodes x,y in the area.
  • the expected signal strengths can be held in a table.
  • the computation of the expected signal strengths can be combined with calculation of the FNerror function for a node.
  • determining the expected signal strengths (SSEs) at the nodes 104 can be performed by a number of methods and can be adapted as required for a particular application.
  • the determination can use modeling factors to provide more accuracy for the expected signal strengths (SSEs) at the nodes.
  • Exemplary modeling factors include signal propagation, signal propagation with predicted uncertainty, known obstructions, potential obstruction probabilities, air humidity, and the like.
  • the signal propagation i.e., the radiation pattern from the field devices, can be modeled using a method such as ray tracing.
  • the signal propagation can optionally account for predicted uncertainty in the radiation pattern
  • a more complex and accurate model of the decay of the radiation pattern with distance rather than fn(x) equals (x ⁇ -3.5), can be used.
  • the decay of the radiation pattern with distance can be modeled as fn(x) equals (x ⁇ -2.5), as appropriate for certain indoor environments.
  • known obstructions within the area can be modeled to account for reflection and/or attenuation of the signals.
  • a user interface can be used to input the location and nature of known obstructions.
  • traffic patterns can be modeled as potential obstruction probabilities to account for the likelihood of people and/or objects being in the area and changing the signal strength.
  • expected air humidity can be can be modeled to account for attenuation of the signals.
  • a user interface or other automated sensor input can be included to input humidity throughout the area and/or in particular regions of the area.
  • the method 100 can account for field devices being offline by detecting when at least one field device is offline, and determining expected signal strengths accounting for the at least one offline field device.
  • An offline field device no longer generates a signal, so the expected signal strengths calculated initially for the set of fingerprints are no longer representative of the expected signal strengths in the area.
  • the target device will see no signal from the offline field device and interpret the signal strength as indicating the particular field device is far away, resulting in poor target device location detection.
  • a user interface can be included to input any field devices that are offline. The function FNerror used in determining at least one of the valid nodes for which the actual signal strengths closely agree with the expected signal strengths can then disregard terms for the offline field devices.
  • a target device record can be constructed of the actual signal strengths with record MeasuredRecord equal to ⁇ signalLevelFromNodeA; signalLevelFromNodeB; ...; signalLevelFromNodeX ⁇ including signal levels received at the target device from each of the field device nodes.
  • Designating as valid nodes the nodes having the expected signal strength (SSE) for a particular field device that is greater than or equal to the actual signal strength (SSA) for a particular field device 108 accounts for the physical behavior of the signals.
  • SSE expected signal strength
  • SSA actual signal strength
  • a valid reading for the actual signal strength for a particular field device at a particular node is less than on approximately equal to the expected signal strength. That is, the signal is much more likely to be attenuated or absorbed compared to the physical model, than the signal is likely to be increased.
  • the target device and particular field device are probably ten meters apart if the path between them is unobstructed and not faded, or somewhat nearer than ten meters apart if the path is obstructed or faded: it is unlikely that the target device and particular field device are further apart.
  • nodes having an actual signal strength for a particular field device that is greater than the expected signal strength can be ignored as invalid nodes and the valid nodes alone used in locating the target device.
  • equal as defined herein includes approximately equal, so that a valid node with an expected signal strength greater than or equal to the actual signal strength can include a node with the actual signal strength being slightly larger than the expected signal strength, as desired for a particular application.
  • Determining at least one of the valid nodes for which the actual signal strengths (SSAs) for the field devices agree with the expected signal strengths (SSEs) for the field devices at the at least one of the valid nodes 110 selects the node where the target device is most likely to be located, i.e., where the fingerprint of the expected signal strengths from the field devices matches the actual signal strengths detected at the target device. Agreement is defined herein as occurring when the actual signal strengths (SSAs) and the expected signal strengths (SSEs) match in a manner and to a degree appropriate for the determination method. In one embodiment, the actual signal strengths (SSAs) agree with the expected signal strengths (SSEs) when the error between the actual signal strengths (SSAs) and the expected signal strengths (SSEs) is minimized.
  • the actual signal strengths (SSAs) agree with the expected signal strengths (SSEs) when the error between the actual signal strengths (SSAs) and the expected signal strengths (SSEs) is no more than a predetermined error value.
  • the actual signal strengths (SSAs) agree with the expected signal strengths (SSEs) when the pattern discerned by a viewer of the distribution of the error sums on a visual display for all nodes individually indicates to the viewer the most likely node for the target device.
  • the actual signal strengths (SSAs) agree with the expected signal strengths (SSEs) when the averaging of node locations for nodes indicates the most likely node for the target device.
  • the record MeasuredRecord containing the actual signal strengths at the target device can be compared against each of the possible RecordContents (x,y) values including expected signal strengths at each node to find the best fit.
  • a least squares method is used, with FNerror defined as a least-squares function which compares two records such that FNerror [record1, record2] equals the square root of: record ⁇ 1 : valueA - record ⁇ 2 : valueA ⁇ ⁇ 2 + ( record ⁇ 1 : valueB - record ⁇ 2 : valueB ⁇ ⁇ 2 + ... + record ⁇ 1 : valueX - record ⁇ 2 : valueX ⁇ ⁇ 2 .
  • the best estimate of location of the target device is the (x,y) location where FNerror [RecordContents (x,y), MeasuredRecord] is the smallest.
  • likely or possible nodes where the target device may be located can be presented in a graph and/or list. The probability that the target device is at a given node can be included on the graph or list.
  • FNerror is presented on a three dimensional graph with node locations on the x,y axes and FNerror as an indication of probability on the z axis.
  • fluctuation in the actual signal strengths can be used to determine when a moving object, such as a person or other object which interferes with the signals from the field devices, is in the area of the field devices.
  • First actual signal strengths can be measured for the target device for each of the field devices in communication with the target device, with each actual signal strength being associated with one of the field devices.
  • Second actual signal strengths for each of the field devices in communication with the target device can then be measured.
  • the second actual signal strengths can be compared to the first actual signal strengths and a probability that an object is moving a the area determined based on the comparing.
  • the expected signal strengths can be weighted for a predictable variation in signal strength when determining at least one of the valid nodes for which the actual signal strengths for the field devices agree with the expected signal strengths for the field devices at the at least one of the valid nodes 110.
  • a statistical method can be used to account for fluctuating signal strength from a fluctuating signal.
  • a set of actual signal strengths (MeasuredRecords) can be recorded at different times and used to assess whether the signals are constant or fluctuating.
  • the maximum actual signal strength measured over time for each particular field device is treated as the best estimate of the actual signal strength and can be determined from the set of actual signal strengths.
  • the maximum actual signal strength can be used in place of a single actual signal strength value in the FNerror function.
  • the likelihood of signal obstruction can be calculated for each of the field devices by dividing the minimum actual signal strength from the set of actual signal strengths for a particular field device by the maximum actual signal strength for the particular field device.
  • the likelihood of signal obstruction can be used to determine when to weight the FNerror function for one of the field devices: an error factor can be applied to the FNerror function to produce a high error number when unexpected conditions are detected. Examples of unexpected conditions include when actual signal strength for a particular field device is much less than the typically expected signal strength, so the particular field device appears to be obstructed when normally unobstructed, or when actual signal strength for a particular field device is much greater than the maximum actual signal strength, so the particular field device appears to be unobstructed when normally obstructed. Thus, the likelihood of signal obstruction enters into the fingerprinting assessment.
  • the FNerror function can be weighted to give higher errors when actual signal strength is higher than expected signal strength at a node.
  • the FNerror function term for the node in which the actual signal strength is higher than expected signal strength can be multiplied by a predetermined penalty factor, such as a factor of five. The weighting is based on the observation that an actual signal strength is generally similar to or less than an expected signal strength predicted by physics for the distance between two nodes, since obstructions absorb the signal.
  • the nodes having the expected signal strength for a particular field device that is less than the actual signal strength for a particular field device can be designated as.high error valid nodes and enter into the determination of at least one of the valid nodes, including the high error valid nodes, for which the actual signal strengths for the field devices agree with the expected signal strengths for the field devices at the at least one of the valid nodes 110 .
  • the determining at least one of the valid nodes includes determining at least one of the valid nodes minimizing an error function FNerror comparing the actual signal strengths for the field devices with the expected signal strengths. Error terms for the high error valid nodes are multiplied by a predetermined penalty factor to penalize the high error valid nodes relative to the other valid nodes.
  • the location detection method can include additional environmental parameters in determining the location of the target device.
  • the method 100 can include determining an expected secondary location parameter at the nodes; measuring an actual secondary location parameter at the at least one of the valid nodes for which the actual signal strengths agree with the expected signal strengths; and comparing the expected secondary location parameter to the actual secondary location parameter.
  • Secondary location parameters are defined herein as any environmental parameter that can be detected in the area. Exemplary secondary location parameters include WiFi signal strength, temperature, electrical noise, light level, sound level, and the like.
  • the location detection method can include feedback as to the correctness of the location determined.
  • the method 100 can include determining an expected node location for the at least one of the valid nodes for which the actual signal strengths for the field devices agree with the expected signal strengths for the field devices at the one of the valid nodes; measuring an actual node location of the at least one of the valid nodes for which the actual signal strengths closely agree with the expected signal strengths; and comparing the expected node location to the actual node location.
  • the actual node location can be measured with a mobile device, such as an optional sensing device.
  • the expected signal strengths can be corrected for any differences discovered from comparing the expected node location to the actual node location.
  • the location detection method can employ evolutionary algorithm modeling.
  • the computational load is reduced in evolutionary algorithm modeling by calculating expected signal strengths for a limited number of nodes in the area, rather than all the nodes in the area.
  • Evolutionary algorithms such as genetic systems based on genetic algorithms (GAs) or artificial immune systems based on artificial immune system algorithms (AISs), select the most likely locations for the target device and calculate expected signal strengths for nodes around the most likely locations. Therefore, expected signal strengths do not have to be calculated initially for all the nodes in the area and expected signal strengths can be calculated when needed.
  • the expected signal strengths are stored for future use when calculated to avoid recalculation when needed for future use.
  • Evolutionary algorithms depend on determining how well an individual, i.e., an individual potential solution to a problem, solves that problem. The measure of this quality is called the fitness of the individual. Individuals of high fitness are more likely to contribute to the development of the subsequent populations of individuals which are tested as solutions to the problem. For the problem of location detection, fitness can be determined by the FNerror function with high fitness individuals being those that minimize the difference in signal strengths between the actual and expected signal strengths.
  • Evolutionary algorithms are optimization algorithms for solving problems and generally follow a high level algorithm including 1) generating a random population of individuals which are potential solutions to the problem; 2) evaluating the fitness of each individual, i.e., determining how well each individual solves the problem; 3) evolving a new population of individuals which are potential solutions to the problem in light of the evaluated fitness; and 4) repeating the evaluating and the evolving until termination when a stopping criterion, such as the number of iterations or a predetermined fitness value, is met.
  • a stopping criterion such as the number of iterations or a predetermined fitness value
  • the evolutionary algorithms can be applied to the location detection method 100.
  • determining expected signal strengths 104 the expected signal strengths from the field devices at the nodes are determined for an initial population of nodes selected at random.
  • Determining at least one of the valid nodes 110 includes testing fitness of the initial population; evolving at least one additional population of nodes from the initial population based on the fitness; testing fitness of the at least one additional population; and determining at least one of the valid nodes as location of the target device based on a criteria selected from the group consisting of a predetermined fitness value and a predetermined number of iterations.
  • the evolving at least one additional population can include evolving at least one additional population with a system selected from genetic systems and artificial immune systems, i.e., applying genetic systems based on genetic algorithms or artificial immune systems based on artificial immune system algorithms.
  • the random population of a predetermined number of individuals is a set of randomly selected nodes (x,y) in the area.
  • the target device may be located on or near one of the nodes, although the likelihood is random due to the random selection.
  • Fitness is evaluated by calculating or looking up the expected signal strength for each individual (RecordContents (x,y)) and comparing the expected signal strength to the actual signal strenght measured at the target device (MeasuredRecord) using the ENerror function. High fitness individuals, which are closest to solving the problem and locating the target device, have the lowest FNerror values. In one embodiment, the FNerror values can be normalized between 0 and 1.
  • Evolving a new population of individuals depends on the type of evolutionary algorithm used, such as genetic or artificial immune system algorithms, but the new population includes high fitness individuals from the present generation (best fitting nodes) and new individuals evolved from the high fitness individuals (new nodes). Fitness is evaluated for the new population, another new population evolved, and the process repeated until the fitness meets a desired criteria indicating the highest fitness node is the location of the target device, or until the predetermined number of iterations have been completed at which point the highest fitness node is designated as the most likely location of the target device.
  • the genetic systems based on genetic algorithms and artificial immune systems based on artificial immune system algorithms differ in their methods of evolving a new population of individuals.
  • two or more high fitness individuals (best fitting nodes) from the present generation are selected as parent nodes and new individual nodes (new nodes) evolved from the parent nodes.
  • two parents are randomly selected (in one example, based on a method which has a bias towards high fitness individuals), crossed-over, and mutated. These two *new* individuals are then added to the child population. This process repeats until the child population is the same size as the main population, whereupon the child population becomes the main population for the next iteration.
  • the new individual nodes are nodes at an average position between the parent nodes.
  • crossover and mutation could occur. Both operations are typically based on predetermined probabilities, e.g., crossover might occur with an 80% probability, whereas mutation might only occur with 5%. The average position between the two parents may be another possible form of crossover. These would then possibly be mutated.
  • the new population includes a fraction of the best fitting nodes from the previous generation and a number of new individual nodes. In another embodiment, the new population includes only the new individual nodes.
  • the poorest fitting nodes from a population can be discarded, although some can be retained within the population as desired to maintain diversity and avoid incorrect convergence.
  • the next (child) population can be created as described above, without any poor nodes removed.
  • the population size remains constant because the previous generation is completely lost: for this reason, a fraction of the best fitting nodes from the parent population are usually kept in the child population.
  • the genetic algorithm can be expressed as:
  • an artificial immune system algorithm For artificial immune systems based on artificial immune system algorithms, high fitness individuals are cloned and mutated to evolve a new population of individuals.
  • One type of an artificial immune system algorithm is based on the clonal selection theory, which employs fitness proportional cloning and inverse proportional mutation, such as implemented in the CLONALG clonal selection algorithm.
  • the combination of cloning proportional to fitness and mutation inversely proportional to fitness allows the artificial immune system algorithm to perform a localized search around current, good solutions.
  • Fitness is also known as affinity for artificial immune systems based on artificial immune system algorithms.
  • a predetermined number of high fitness individuals are selected for cloning and are cloned according to their fitness. The better the fitness of the individual, the more clones of that individual are produced. For example, the highest fitness individual can be cloned into five clones, the next highest into three clones, and the next highest into one clone. Those skilled in the art will appreciate that other cloning strategies to determine the number of clones can be used as desired for a particular application.
  • the clones are mutated, with the degree of mutation inversely proportional to the fitness of the clone. The better the fitness of the clone, the less mutation that is needed to move the clone toward the optimum solution.
  • the distance from the clone to the mutated node depends on the fitness of the clone.
  • the mutated node is selected a distance away from the clone that is inversely proportional to the fitness of the clone. The fitter the clone, the closer it is to the desired solution, and so the less mutation needed to get to the solution.
  • the constituent components of the FNerror calculation such as the error from each of the field devices are analyzed and the mutated node is shifted in distance and direction to reduce the FNerror value.
  • the direction of mutation depends on what information is available for calculation. In one embodiment with only a fitness value available, direction is random. When further information can be discerned, for example, when the signal strengths from each field device are considered individually, the direction of mutation can possibly be influenced further. In one example, mutations can be made to reduce individual component signal strength errors. In another example, a direction can be chosen based on a statistical distribution (e.g., a normal distribution) around an angle which is likely to improve the fitness. This angle can be based on the angle to a field device that currently has the lowest signal strength error (in an attempt to make it fitter), or the angle with the greatest signal strength error (in an attempt to make it fitter). Those skilled in the art will appreciate that a number of variations are possible.
  • the overall direction of movement of individuals is influenced by the process of fitness calculation, clone generation, and mutation. Mutated clones can be generated in a random direction; those who are fitter than the parent will more produce more clones themselves (than the parent and siblings) in the next iteration, and therefore form the center of the next round of searching. Over a number of iterations, the effective center of the search can be considered to move in one or more directions based on the improving fitness of the children.
  • the fitness values can be calculated for the mutated nodes.
  • the mutated node with the highest fitness value can be stored in a memory or solution set population of individuals, which is different than the main population of individuals used in the cloning.
  • the individual stored as the current most probable location can only be replaced in subsequent iterations by an individual of higher fitness, but not an individual of lower fitness.
  • a predetermined number of mutated nodes with the highest fitness values can be stored as the current most probable locations for the target device. For example, the five most probable mutated nodes could be stored.
  • a measure of the grouping closeness in location of the predetermined number of mutated nodes can be calculated to determine how likely it is that the target device is near the group of mutated nodes. The more closely packed the group in 2D space, the more likely the target device is near the group.
  • the grouping closeness in location can be determined from the sum of the FNerror values for each of the group.
  • FNerror calculates the error in signal strengths based on distances from each field device.
  • Each most probable node could be close together in terms of signal strength, but not in terms of x,y coordinates.
  • a cluster measurement can be performed based on the 2D distances between the most probable nodes.
  • the center of the most probable nodes (mean average of each coordinate dimension) can be calculated and the sum of distances (or alternatively, the average distance) between each node and this center. The more compact the cluster (i.e., the lower the sum, or lower the average distance), the smaller and more targeted the area in which the device is likely to be located. This assumes that a smaller, more compact area implies a higher likelihood that the target device is in that area.
  • a large target area has not managed to narrow the location of the target device down to any specific spot.
  • Angles can also be taken into account the most probable nodes form more than one cluster.
  • a threshold value can be used to assign most probable nodes to appropriate clusters. More than one cluster would suggest more than one likely location for the target device. These clusters can be ranked on something by the number of nodes in that cluster. The more nodes in a cluster, the more likely the target device is in that area.
  • the new population can then be created.
  • a predetermined number of individuals in the population including the mutated nodes can be replaced with randomly generated individuals.
  • the cloned/mutated nodes can be kept separate from the main population or can be integrated with the main population. Replacing a portion of the population with randomly generated individuals performs a global search, looking for new good solution areas over the potential solution space to the problem, as well as helping the artificial immune system algorithm escape local minima.
  • a predetermined number of nodes with the lowest fitness values are replaced with randomly generated individuals.
  • the fitness values are used as a selection mechanism, with the fitness values being used as weighting factors and the replacement of a given individual determined by probabilistic methods including its weighting factor. For example, selection can be an inverse roulette wheel selection.
  • the new population evolved using a genetic system algorithm or an artificial immune system algorithm can be repeatedly evaluated and evolved until termination, when a stopping criterion is met.
  • exemplary stopping criterion include a predetermined number of iterations, or a predetermined fitness value indicating that a location has been found with expected signal strengths close to the actual signal strengths.
  • FIG. 4 is a flowchart of another location detection method in accordance with some embodiments of the present invention.
  • the target node transmits a signal and the field devices detect the signal.
  • the field devices can report the actual signal strengths to an optional control unit for computation.
  • the method 200 includes defining nodes in an area 202, the area being associated with a target device and field devices; determining expected signal strengths from the target device at the field devices 204, each expected signal strength at a particular field device being associated with one of the nodes; measuring actual signal strengths from the target device at the field device 206 for each of the field devices in communication with the target device , each actual signal strength being associated with one of the field devices; designating as valid nodes the nodes having the expected signal strength for the particular field device that is greater than or equal to the actual signal strength for the particular field device 208; and determining at least one of the valid nodes for which the actual signal strengths for the field devices agree with the expected signal strengths for the field devices at the at least one of the valid nodes 210.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biophysics (AREA)
  • General Physics & Mathematics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Theoretical Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Genetics & Genomics (AREA)
  • Molecular Biology (AREA)
  • Biomedical Technology (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Physiology (AREA)
  • Position Fixing By Use Of Radio Waves (AREA)

Claims (10)

  1. Standorterkennungsverfahren, das die nachfolgenden Verfahrensschritte umfasst:
    das Definieren von Knoten in einem Gebiet, wobei das Gebiet Feldeinrichtungen und einer Zieleinrichtung (102) zugeordnet ist;
    das Ermitteln erwarteter Signalstärken aus den Feldeinrichtungen in den Knoten, wobei jede erwartete Signalstärke in jedem Knoten einer der Feldeinrichtungen (104) zugeordnet ist;
    das Messen der wirklichen Feldstärken aus den Feldeinrichtungen in der Zieleinrichtung für jede der Feldeinrichtungen in Zusammenarbeitet mit der Zieleinrichtung, wobei jede wirkliche Signalstärke einer der Feldeinrichtungen (106) zugeordnet ist;
    das Bezeichnen einiger der genannten Knoten als gültige Knoten (108); und
    das Bestimmen, und zwar als den Standort der Zieleinrichtung, eines der gültigen Knoten, für welche die wirklichen signalstärken für die Feldeinrichtungen den erwarteten Signalstärken für die Feldeinrichtungen in dem genannten einen der gültigen Knoten (110) entsprechen;
    dadurch gekennzeichnet, dass:
    die als gültige Knoten bezeichneten Knoten nur diejenigen Knoten sind, welche die erwartete Signalstärke für jede der Feldeinrichtungen in Zusammenarbeit mit der Zieleinrichtung haben, die größer ist als die aus der betreffenden Feldeinrichtung gemessene wirkliche Signalstärke oder dieser entspricht.
  2. Verfahren nach Anspruch 1, wobei das Ermitteln erwarteter Signalstärken weiterhin das Ermitteln erwarteter Signalstärken unter Verwendung von Modellierfaktoren, selektiert aus der Gruppe, bestehend aus Signalfortpflanzung, Signalfortpflanzung mit vorhergesagter Ungewissheit, bekannter Obstruktionen, möglicher Obstruktionswahrscheinlichkeiten und Luftfeuchtigkeit.
  3. Verfahren nach Anspruch 1, das weiterhin das Empfangen eines Eingangssignals über eine Benutzerschnittstelle umfasst, wobei dieses Signal wenigstens eine lokale Feldeinrichtung identifiziert, und wobei das Ermitteln erwarteter Signalstärken weiterhin das Ermitteln erwarteter Signalstärken unter Berücksichtigung der wenigstens einen lokalen Feldeinrichtung umfasst.
  4. Verfahren nach Anspruch 1, das weiterhin Folgendes umfasst:
    das Ermitteln eines erwarteten sekundären Ortsparameter in den Knoten;
    das Messen eines wirklichen sekundären Ortsparameters in dem wenigstens einen der gültigen Knoten, für welche die wirklichen signalstärken den erwarteten Signalstärken entsprechen; und
    das Vergleichen des erwarteten sekundären Ortsparameters mit dem wirklichen sekundären Ortsparameter.
  5. Verfahren nach Anspruch 4, wobei der wirkliche sekundäre Ortsparameter aus der Gruppe selektiert wird, bestehend aus WiFi-Signalstärke, Temperatur, elektrische Störung, Lichtpegel und Schallpegel.
  6. Verfahren nach Anspruch 1, das weiterhin Folgendes umfasst: das Schätzen eines Standorts wenigstens einer Feldeinrichtung aus einem bekannten Standort einer festen Feldeinrichtung.
  7. Verfahren nach Anspruch 1, wobei das Ermitteln wenigstens eines der gültigen Knoten weiterhin das Gewichten der erwarteten Signalstärken für eine vorhersagbare Abweichung in der Signalstärke umfasst.
  8. Verfahren nach Anspruch 1, wobei das Ermitteln erwarteter Signalstärken das Ermitteln erwarteter Signalstärken aus den Feldeinrichtungen in den Knoten für eine Ausgangsbesetzung beliebig selektierter Knoten umfasst; und
    wobei das Ermitteln wenigstens eines der gültigen Knoten Folgendes umfasst:
    das Testen der Tauglichkeit der Ausgangsbesetzung;
    das Entwickeln wenigstens einer zusätzlichen Besetzung von Knoten aus der Ausgangsbesetzung, und zwar auf Basis der Tauglichkeit;
    das Testen der Tauglichkeit der wenigstens einen zusätzlichen Besetzung; und
    das Ermitteln wenigstens eines der gültigen Knoten als Standort der Zieleinrichtung, und zwar auf Basis von Kriterien, selektiert aus der Gruppe, bestehend aus einem vorher bestimmten Tauglichkeitswert und einer vorher bestimmten Anzahl Wiederho lungen.
  9. Verfahren nach Anspruch 8, wobei das Entwickeln wenigstens einer zusätzlichen Besetzung das Entwickeln wenigstens einer zusätzlichen Besetzung mit einem System, selektiert aus der Gruppe, bestehend aus genetischen Systemen und künstlichen immunen Systemen umfasst.
  10. Standorterkennungssystem, das Folgendes umfasst:
    eine Zieleinrichtung (40);
    Feldeinrichtungen (30); und
    einen Prozessor (74), der zu den nachfolgenden Zwecken wirksam ist:
    zum Bestimmen erwarteter Signalstärken aus den Feldeinrichtungen in Knoten in einem Gebiet, wobei jede erwartete Signalstärke in jedem Knoten einer der Feldeinrichtungen (104) zugeordnet ist;
    zum Messen wirklicher Feldstärken aus den Feldeinrichtungen in der Zieleinrichtung für jede der Feldeinrichtungen in Zusammenarbeitet mit der Zieleinrichtung, wobei jede wirkliche Signalstärke einer der Feldeinrichtungen (106) zugeordnet ist;
    zum Bezeichnen einiger der genannten Knoten als gültige Knoten; und
    zum Bestimmen, und zwar als den Standort der Zieleinrichtung, eines der gültigen Knoten, für welche die wirklichen signalstärken für die Feldeinrichtungen den erwarteten Signalstärken für die Feldeinrichtungen in dem genannten einen der gültigen Knoten (110) entsprechen;
    dadurch gekennzeichnet, dass:
    die als gültige Knoten bezeichneten Knoten nur diejenigen Knoten sind, welche die erwartete Signalstärke für jede der Feldeinrichtungen in Zusammenarbeit mit der Zieleinrichtung haben, die größer ist als die aus der betreffenden Feldeinrichtung gemessene wirkliche Signalstärke oder dieser entspricht.
EP10715356.1A 2009-03-23 2010-03-09 Standorterkennungssystem und -verfahren mit fingerabdrücken Not-in-force EP2411831B1 (de)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US16248509P 2009-03-23 2009-03-23
PCT/IB2010/051010 WO2010109361A1 (en) 2009-03-23 2010-03-09 Location detection system and method with fingerprinting

Publications (2)

Publication Number Publication Date
EP2411831A1 EP2411831A1 (de) 2012-02-01
EP2411831B1 true EP2411831B1 (de) 2014-06-11

Family

ID=42236611

Family Applications (1)

Application Number Title Priority Date Filing Date
EP10715356.1A Not-in-force EP2411831B1 (de) 2009-03-23 2010-03-09 Standorterkennungssystem und -verfahren mit fingerabdrücken

Country Status (8)

Country Link
US (1) US9335399B2 (de)
EP (1) EP2411831B1 (de)
JP (1) JP5818779B2 (de)
KR (1) KR101726150B1 (de)
CN (1) CN102362193B (de)
CA (1) CA2756019C (de)
TW (1) TW201041418A (de)
WO (1) WO2010109361A1 (de)

Families Citing this family (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012517041A (ja) * 2009-02-05 2012-07-26 日本電気株式会社 遺伝的アプローチによる期限付きタスクの受付制御・スケジューリング方法、システムおよびプログラム
US8472973B2 (en) 2010-04-23 2013-06-25 Microsoft Corporation Adaptive energy-efficient location determination
US9996057B2 (en) * 2011-06-07 2018-06-12 Philips Lighting Holding B.V. Methods for automatically commissioning of devices of a networked control system
KR101668784B1 (ko) 2011-09-23 2016-10-24 퀄컴 인코포레이티드 근접 핑거프린트들을 통한 포지션 추정
CN103068035B (zh) * 2011-10-21 2016-03-02 中国移动通信集团公司 一种无线网络定位方法、装置及系统
KR20140058996A (ko) * 2012-11-07 2014-05-15 삼성전자주식회사 사용자 단말, 외부 장치, 데이터 송수신 시스템 및 데이터 송수신 방법
US9766603B2 (en) 2013-03-08 2017-09-19 International Business Machines Corporation Wireless network of low power sensing and actuating motes
US9253596B2 (en) * 2013-10-15 2016-02-02 Qualcomm Incorporated Method and apparatus for detecting location changes and monitoring assistance data via scanning
CN105050101B (zh) * 2014-04-28 2020-04-03 维亚威解决方案英国有限公司 用于导出信号强度衰减特征值的方法和装置
US9438621B2 (en) * 2014-07-17 2016-09-06 The Boeing Company Dendritic cell algorithm module with inflammatory inter-node signaling
WO2016096010A1 (en) * 2014-12-18 2016-06-23 Here Global B.V. Checking the health of radio model data
EP3356839B1 (de) * 2015-09-30 2022-04-06 HERE Global B.V. Überprüfung von fingerabdrucksproben für ein radiomodell
JP6396355B2 (ja) * 2016-03-29 2018-09-26 セコム株式会社 端末所持者検知システム
KR101827107B1 (ko) * 2016-05-04 2018-02-07 두산중공업 주식회사 무선측위 오차율을 최소화하는 무선측위 시스템 및 방법
KR20180071095A (ko) 2016-12-19 2018-06-27 삼성전자주식회사 위치 정보 제공 방법 및 그 장치
US10627479B2 (en) * 2017-05-17 2020-04-21 Zerokey Inc. Method for determining the position of an object and system employing same
EP3418831B1 (de) * 2017-06-19 2023-08-16 C.R.F. Società Consortile per Azioni Verfahren zur durchführung eines rauschentfernungsvorgangs auf von einem sensor erfassten signalen und system daraus
KR102139970B1 (ko) * 2018-04-25 2020-07-31 가천대학교 산학협력단 오차의 가중치 합의 최적화를 활용한 실내 무선 측위 방법 및 장치
US11968592B2 (en) 2018-10-15 2024-04-23 Paylessgate Corporation Position determination system, position determination apparatus, position determination method, position determination program, and computer-readable storage medium and storage device
US11044797B2 (en) 2018-12-21 2021-06-22 Signify Holding B.V. Method of and device for commissioning a lighting system
EP4034903A4 (de) * 2019-09-25 2024-01-24 Nokia Solutions & Networks Oy Verfahren und vorrichtung zur sensorauswahl zur lokalisierung und verfolgung
CN111060871A (zh) * 2019-12-26 2020-04-24 南京长峰航天电子科技有限公司 一种基于改进遗传算法的五元阵定位方法和装置
GB2594737A (en) * 2020-05-06 2021-11-10 Ekkosense Ltd Data centre monitoring

Family Cites Families (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3165391B2 (ja) 1996-03-22 2001-05-14 松下電器産業株式会社 移動体無線通信システムとその移動局の位置検出方法
WO1998010307A1 (en) * 1996-09-09 1998-03-12 Dennis Jay Dupray Location of a mobile station
GB9702021D0 (en) * 1997-01-31 1997-03-19 Imperial College Medicaments
US5977913A (en) 1997-02-07 1999-11-02 Dominion Wireless Method and apparatus for tracking and locating personnel
US20030146871A1 (en) 1998-11-24 2003-08-07 Tracbeam Llc Wireless location using signal direction and time difference of arrival
SE524509C2 (sv) * 2002-04-23 2004-08-17 Axis Ab Metod och anordning för bestämning av positionen för en bärbar anordning
US7538715B2 (en) 2004-10-04 2009-05-26 Q-Track Corporation Electromagnetic location and display system and method
US7298314B2 (en) 2002-08-19 2007-11-20 Q-Track Corporation Near field electromagnetic positioning system and method
US7460505B2 (en) * 2003-02-04 2008-12-02 Polaris Wireless, Inc. Location estimation of wireless terminals through pattern matching of signal-strength differentials
US7233799B2 (en) * 2003-02-24 2007-06-19 Polaris Wireless, Inc. Location estimation of wireless terminals based on combinations of signal strength measurements and geometry-of-arrival measurements
US20040166877A1 (en) * 2003-02-24 2004-08-26 David Stevenson Spain Database for locating wireless terminals based on combinations of signal-strength measurements and geometry-of-arrival measurements
WO2005011321A1 (en) * 2003-07-19 2005-02-03 Polaris Wireless, Inc. Location estimation of wireless terminals through pattern matching of deduced and empirical signal-strength measurements
US7116987B2 (en) * 2003-07-19 2006-10-03 Polaris Wireless, Inc. Location estimation of wireless terminals through pattern matching of deduced and empirical signal-strength measurements
SE527308C2 (sv) * 2003-10-20 2006-02-07 Ericsson Telefon Ab L M Apparater och förfarande för fördeling av resurser mellan celler i ett mobilkommunikationsnät
US7433696B2 (en) * 2004-05-18 2008-10-07 Cisco Systems, Inc. Wireless node location mechanism featuring definition of search region to optimize location computation
US7286835B1 (en) * 2004-09-10 2007-10-23 Airespace, Inc. Enhanced wireless node location using differential signal strength metric
US8483704B2 (en) * 2005-07-25 2013-07-09 Qualcomm Incorporated Method and apparatus for maintaining a fingerprint for a wireless network
US8477731B2 (en) * 2005-07-25 2013-07-02 Qualcomm Incorporated Method and apparatus for locating a wireless local area network in a wide area network
FI118715B (fi) * 2005-12-07 2008-02-15 Ekahau Oy Paikannustekniikka
EP1821116B1 (de) * 2006-02-15 2013-08-14 Sony Deutschland Gmbh Relative 3D-Positionierung in einem Ad-hoc-Netzwerk auf Distanzbasis
JP4689496B2 (ja) * 2006-02-27 2011-05-25 京セラ株式会社 無線端末装置及びその制御方法並びに無線基地局装置
JP2008148136A (ja) * 2006-12-12 2008-06-26 Toshiba Corp 無線通信端末
JP4910933B2 (ja) * 2007-08-08 2012-04-04 株式会社日立プラントテクノロジー 無線情報通信システム
US8103441B2 (en) * 2008-06-26 2012-01-24 Microsoft Corporation Caching navigation content for intermittently connected devices

Also Published As

Publication number Publication date
JP2012521557A (ja) 2012-09-13
KR20120019435A (ko) 2012-03-06
CA2756019C (en) 2016-11-15
CA2756019A1 (en) 2010-09-30
US9335399B2 (en) 2016-05-10
TW201041418A (en) 2010-11-16
CN102362193A (zh) 2012-02-22
JP5818779B2 (ja) 2015-11-18
CN102362193B (zh) 2013-11-20
EP2411831A1 (de) 2012-02-01
KR101726150B1 (ko) 2017-04-12
US20120021768A1 (en) 2012-01-26
WO2010109361A1 (en) 2010-09-30

Similar Documents

Publication Publication Date Title
EP2411831B1 (de) Standorterkennungssystem und -verfahren mit fingerabdrücken
Khodayari et al. A RSS-based fingerprinting method for positioning based on historical data
He et al. INTRI: Contour-based trilateration for indoor fingerprint-based localization
JP5048021B2 (ja) 建物影響推定装置及び建物影響推定方法
TW201329486A (zh) 定位方法
Alshami et al. Automatic WLAN fingerprint radio map generation for accurate indoor positioning based on signal path loss model
Leng et al. Cooperative and distributed localization for wireless sensor networks in multipath environments
Sadhukhan et al. A novel weighted fusion based efficient clustering for improved Wi-Fi fingerprint indoor positioning
Das et al. Node position estimation for efficient coverage hole-detection in wireless sensor network
Yu et al. An adaptive model recognition and construction method for RSSI fingerprint-based localization
Al-Ahmadi et al. Single-phase wireless LAN based multi-floor indoor location determination system
Xu et al. Variance-based fingerprint distance adjustment algorithm for indoor localization
Biswas et al. New RSSI-fingerprinting-based smartphone localization system for indoor environments
Ye et al. A novel adaptive radio map for RSS‐based indoor positioning
Gadhgadhi et al. Distance estimation using polynomial approximation and neural network based on rssi technique
Berkvens et al. Signal strength indoor localization using a single DASH7 message
Li et al. Target tracking using signal strength differences for long-range IoT networks
Ishida et al. A robust indoor localization method for NLOS environments utilizing sensor subsets
Mitilineos et al. WAX-ROOM: an indoor WSN-based localization platform
Jegede et al. A genetic algorithm for node localization in wireless sensor networks
Chiu et al. An Adaptive Location-Based Tracking Algorithm Using Wireless Sensor Network for Smart Factory Environment
Song et al. Convex feasibility problem based geometric approach for device-free localization
Hatthasin et al. An improvement of an RFID indoor positioning system using one base station
Kokkinis Improving indoor localization accuracy through information fusion
Jain et al. Distributed growing radial basis function neural networks for location estimation in indoor wireless networks

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

17P Request for examination filed

Effective date: 20111024

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO SE SI SK SM TR

DAX Request for extension of the european patent (deleted)
17Q First examination report despatched

Effective date: 20120910

RAP1 Party data changed (applicant data changed or rights of an application transferred)

Owner name: KONINKLIJKE PHILIPS N.V.

REG Reference to a national code

Ref country code: DE

Ref legal event code: R079

Ref document number: 602010016632

Country of ref document: DE

Free format text: PREVIOUS MAIN CLASS: G01S0005020000

Ipc: G06N0003120000

GRAP Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOSNIGR1

RIC1 Information provided on ipc code assigned before grant

Ipc: G06N 3/12 20060101AFI20131204BHEP

Ipc: G01S 5/02 20100101ALI20131204BHEP

INTG Intention to grant announced

Effective date: 20140109

GRAS Grant fee paid

Free format text: ORIGINAL CODE: EPIDOSNIGR3

GRAA (expected) grant

Free format text: ORIGINAL CODE: 0009210

AK Designated contracting states

Kind code of ref document: B1

Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO SE SI SK SM TR

REG Reference to a national code

Ref country code: GB

Ref legal event code: FG4D

REG Reference to a national code

Ref country code: CH

Ref legal event code: EP

REG Reference to a national code

Ref country code: IE

Ref legal event code: FG4D

REG Reference to a national code

Ref country code: AT

Ref legal event code: REF

Ref document number: 672557

Country of ref document: AT

Kind code of ref document: T

Effective date: 20140715

REG Reference to a national code

Ref country code: DE

Ref legal event code: R096

Ref document number: 602010016632

Country of ref document: DE

Effective date: 20140724

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: GR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20140912

Ref country code: NO

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20140911

Ref country code: FI

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20140611

Ref country code: LT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20140611

REG Reference to a national code

Ref country code: NL

Ref legal event code: VDEP

Effective date: 20140611

REG Reference to a national code

Ref country code: AT

Ref legal event code: MK05

Ref document number: 672557

Country of ref document: AT

Kind code of ref document: T

Effective date: 20140611

REG Reference to a national code

Ref country code: LT

Ref legal event code: MG4D

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: LV

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20140611

Ref country code: SE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20140611

Ref country code: HR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20140611

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: CZ

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20140611

Ref country code: EE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20140611

Ref country code: PT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20141013

Ref country code: SK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20140611

Ref country code: RO

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20140611

Ref country code: ES

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20140611

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: PL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20140611

Ref country code: NL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20140611

Ref country code: AT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20140611

Ref country code: IS

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20141011

REG Reference to a national code

Ref country code: DE

Ref legal event code: R097

Ref document number: 602010016632

Country of ref document: DE

PLBE No opposition filed within time limit

Free format text: ORIGINAL CODE: 0009261

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: DK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20140611

Ref country code: IT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20140611

26N No opposition filed

Effective date: 20150312

REG Reference to a national code

Ref country code: DE

Ref legal event code: R097

Ref document number: 602010016632

Country of ref document: DE

Effective date: 20150312

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: BE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20140611

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: SI

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20140611

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: MC

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20140611

Ref country code: LU

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20150309

REG Reference to a national code

Ref country code: CH

Ref legal event code: PL

REG Reference to a national code

Ref country code: IE

Ref legal event code: MM4A

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: LI

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20150331

Ref country code: IE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20150309

Ref country code: CH

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20150331

REG Reference to a national code

Ref country code: FR

Ref legal event code: PLFP

Year of fee payment: 7

REG Reference to a national code

Ref country code: GB

Ref legal event code: 732E

Free format text: REGISTERED BETWEEN 20161006 AND 20161012

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: MT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20140611

REG Reference to a national code

Ref country code: DE

Ref legal event code: R082

Ref document number: 602010016632

Country of ref document: DE

Representative=s name: MEISSNER BOLTE PATENTANWAELTE RECHTSANWAELTE P, DE

Ref country code: DE

Ref legal event code: R081

Ref document number: 602010016632

Country of ref document: DE

Owner name: PHILIPS LIGHTING HOLDING B.V., NL

Free format text: FORMER OWNER: KONINKLIJKE PHILIPS N.V., EINDHOVEN, NL

REG Reference to a national code

Ref country code: FR

Ref legal event code: PLFP

Year of fee payment: 8

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: FR

Payment date: 20170327

Year of fee payment: 8

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: BG

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20140611

Ref country code: HU

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT; INVALID AB INITIO

Effective date: 20100309

Ref country code: SM

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20140611

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: GB

Payment date: 20170330

Year of fee payment: 8

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: CY

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20140611

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: DE

Payment date: 20170531

Year of fee payment: 8

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: TR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20140611

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: MK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20140611

REG Reference to a national code

Ref country code: DE

Ref legal event code: R119

Ref document number: 602010016632

Country of ref document: DE

GBPC Gb: european patent ceased through non-payment of renewal fee

Effective date: 20180309

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: DE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20181002

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: GB

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20180309

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: FR

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20180331